This AI actually WORKS!!! - NVIDIA RTX Voice
Channel:ShortCircuit · Length:7:47 · Published:2020-04-23 · Views:1809306
Summary
A ShortCircuit (Linus Tech Tips) review of Nvidia's RTX Voice, which uses GPU-based neural networks to remove background noise from microphone audio. It demonstrates how well the filtering works.
Why HN recommends it
Cited as a demo of GPU-powered noise suppression that works remarkably well, in threads on mic muting and speech enhancement.
It's really pretty impressive, here's a demo — HN, 2021
Computer vision, speech & NLP · Consumer devices & gadgets · Audio & video engineering
Subtitles (excerpt)
- When a company tries to sell you something using AI these days, I immediately get a little bit skeptical. It's kind of just thrown around all over the place, especially at CES. And sometimes it's great, other times not so much. So where does NVIDIA's new RTX Voice fall? Apparently, they can use AI and the RTX cores on your graphics card, that you're probably not actually using, to remove background noise and crap from your stream. Like you know, you're streaming along, and you're using these really inconvenient blue switches that are pretty loud for everyone else, but maybe this will get rid of that. I don't know, let's test it out. I don't have super high hopes for this, but at the same time, I've seen some stuff on Twitch from Barnacules that looks really promising. So, I don't know, let's give it a try, see what the limits are. So, setting up RTX Voice is actually really quite easy. All that you have to do is go to this website right here, and click download the app. It should install pretty easily, assuming that you have a RTX card and the driver 410.18 or newer. So you know, probably good there, that was quite an old one. So pretty much all that you get, is this right here. It's this tiny little window that says NVIDIA RTX Voice.
On Hacker News
> someone else's background or breathing noise NVIDIA Broadcast (Previously called RTX Voice) is a godsend for those scenarios. If you haven't seen it, it's worth checking out. It is absolutely magical. [VIDEO] Sadly, AFAIK, it does require an NVIDIA GPU, but it doesn't need an RTX card. I used it on my GTX 1070 and it worked wonderfully. What's really amazing about it is that you can use it to f… — Sohcahtoa82, 2021-08
If you have an RTX card, get nVidia Broadcast. If you have a non-RTX card (like a GTX 1070), get RTX voice. Despite the name, it does not require an RTX card. Seriously, nVidia's noise removal is absolute magic, as far as I'm concerned. [VIDEO] — Sohcahtoa82, 2021-01
A solution like rtx voice seems a better way to go tbh. For those who don't know, it's an nvidia thing that uses a GPU accelerated (ofc, it's nvidia) neural network to denoise voice calls, from all kinds of noise, not just typing. It's really pretty impressive, here's a demo: [VIDEO] I wish it wasn't proprietary though (and worse, hardware specific). And windows only of course. — wheybags, 2021-01
This remembers me of NVIDIA RTX Voice [0]. Although not made to isolate single persons, this is quite impressive. I hope that this single person isolation will find it's way to consumer noise-cancelling headphones [0] [VIDEO] — i5heu, 2024-05
Nvidia has a similar thing called RTX audio, but its even more impressive and runs live on recording [VIDEO] — jacooper, 2022-12
Related videos
- Are Electric Cars Worse For The Environment? Myth Busted · Engineering Explained · 13:47
- Amiga music: Captain - Space Debris · Kuokka77 · 4:57
- D/A and A/D | Digital Show and Tell (Monty Montgomery @ xiph.org) · FL Studio · 23:52
- Detergent packs are kinda wishy-washy (Dishwashers Explained) · Technology Connections · 32:34
- Behind the Scenes of iOS Security · Black Hat · 51:31
- The Antique Toaster that's Better than Yours · Technology Connections · 18:28
- Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning · Google TechTalks · 48:10
- Guarding Against Physical Attacks: The Xbox One Story — Tony Chen, Microsoft · Platform Security Summit · 58:05
- The world's worst video card? · Ben Eater · 32:47
- "Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea · Strange Loop Conference · 41:17
- BOLTR: Juicero, Cold Press Juicer for Rich Weirdos · AvE · 41:39
- Andrej Karpathy - AI for Full-Self Driving at Tesla · Matroid · 30:08
- Tensorflow and deep learning - without a PhD by Martin Görner · Devoxx · 2:35:53
- JPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile · Computerphile · 15:11
- Fourier Optics used for Optical Pattern Recognition · Huygens Optics · 18:30
- Floyd Toole - Sound reproduction – art and science/opinions and facts · CIRMMT · 1:13:56